cs.CLMay 11, 2026

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models

Authors: Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz

Organizations: Centre for Industrial Software, University of Southern Denmark, Alsion 2, Sønderborg, 6400, Denmark · ProMake, Newark, DE, USA

Abstract

Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption. A checkpoint can appear fixed under evaluation-style prompts while the same behavior persists under ordinary-use prompts. Output scores reveal this mismatch but do not locate it. We investigate whether the distinction is encoded in a stable internal site and introduce an audit that fits a paired activation contrast at a path-patching-informed mid-depth window, then modifies the resulting coordinate on held-out prompts. The intervention reduces the evaluation-to-deployment gap by more than 0.120.12 in ten of twelve model--behavior settings and closes it (post-intervention gap below 0.060.06) in four, across four full-matrix instruction-tuned model instances; among the eight settings with n≥120n{\geq}120 paired questions, six reduce and one closes. A fifth model supports localization and edit-provenance checks, and in the twelve settings deployment-framed rates change by at most 6.16.1pp. On retrained checkpoints, random directions at the same dose do not reproduce the effect, and off-window controls do so only in part. The strongest literal evidence for an evaluation-versus-deployment distinction comes from sandbagging, whose prompt framing is explicitly evaluative; sycophancy and refusal test framing-contingent task distinctions. The two weak cells, both sycophancy, show where a single-coordinate audit at a fixed window is not sufficient. The audit is a non-adaptive, white-box diagnostic for controlled fine-tuned checkpoints, not a training-time defense, a guarantee of deployment safety, or evidence about naturally arising failures.

Figures & tables

Appendix figures & tables26 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Evaluation Awareness in Language Models: Representation, Verbalization, and Control

    Aug 22, 2026Farzaneh Heidari, Amin Memarian, Guillaume RabusseauEvaluation Awareness in Language ModelsLLM Interpretability

  2. Evaluation Awareness Is Not One Capability: Evidence from Open Language Models

    Jun 22, 2026Nilesh Nayan, Aishwarya Sampath Kumar, Rishiraj Girmal +5Language Model Safety EvaluationLLM Interpretability

  3. Mean Accuracy Is the Wrong Estimand for a Release Decision

    Oct 12, 2026Jaewon Choi, Jihye Kang, Namhyuk AhnLLM ReliabilityLLM Evaluation